© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7409
    Prev
    Next
    INDEX
    Explanations

    herbal and medicinal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    🌦
    0.44
    頎
    0.43
     ইঞ্জিনিয়ার
    0.43
     semiconductor
    0.42
     acrylonitrile
    0.42
     ബാറ്ററി
    0.41
     DevOps
    0.41
     engineer
    0.41
    iqués
    0.41
    🌥
    0.41
    POSITIVE LOGITS
     herbal
    1.17
     Herbal
    1.07
     herbs
    1.06
     Herbs
    1.00
     herb
    0.91
     medicinal
    0.88
     herbaceous
    0.84
     Medicinal
    0.79
    herb
    0.75
     Botanical
    0.74
    Activations Density 0.283%

    No Known Activations